Pith. sign in

REVIEW 1 cited by

Weight Expansion: A New Perspective on Dropout and Generalization

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2201.09209 v2 pith:RZMQOH3S submitted 2022-01-23 cs.LG stat.ML

classification cs.LGstat.ML
keywords weightexpansiondropoutgeneralizationemphleadregularizerresp
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

While dropout is known to be a successful regularization technique, insights into the mechanisms that lead to this success are still lacking. We introduce the concept of \emph{weight expansion}, an increase in the signed volume of a parallelotope spanned by the column or row vectors of the weight covariance matrix, and show that weight expansion is an effective means of increasing the generalization in a PAC-Bayesian setting. We provide a theoretical argument that dropout leads to weight expansion and extensive empirical support for the correlation between dropout and weight expansion. To support our hypothesis that weight expansion can be regarded as an \emph{indicator} of the enhanced generalization capability endowed by dropout, and not just as a mere by-product, we have studied other methods that achieve weight expansion (resp.\ contraction), and found that they generally lead to an increased (resp.\ decreased) generalization ability. This suggests that dropout is an attractive regularizer, because it is a computationally cheap method for obtaining weight expansion. This insight justifies the role of dropout as a regularizer, while paving the way for identifying regularizers that promise improved generalization through weight expansion.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Enhancing Robust Fairness via Confusional Spectral Regularization

    cs.LG 2025-01 conditional novelty 5.0 of 10

    A PAC-Bayesian bound ties worst-class robust error to the spectral norm of a robust confusion matrix, and a new spectral regularizer improves robust fairness.

Pith tools